How to find stocks in strong uptrends with ChatGPT or Claude

A starting list for research. It does not recommend any trade.

298 stocks passed at the Nov 5 close, and 89 lacked enough history to decide. The leaders are mostly drug developers, and MRNA and KOD each nearly tripled in a single session in the past three months. MRNA and SYRE each filed an 8-K with item 1.01 in the last 60 sessions, so the pending-deal variation leaves them out.

US stocks, ETFs and futures. The free plan runs 20 queries a day on daily bars; Pro adds intraday.

Paste these into the same chat, after the first answer, so your AI knows which results you mean.

• Chart the top three with their 50, 150 and 200-day averages.

  Copy

• How did each company’s revenue change from a year earlier in its latest report?

  Copy

• Did any of these file an 8-K with item 1.01 or receive a tender offer in the last 60 sessions?

  Copy

• Any insider buying in these over the past three months?

  Copy

A trend template is a checklist growth traders use to keep only stocks already in a strong, orderly uptrend. The price sits above its 50, 150 and 200-day averages, those averages are stacked in that order, the 200-day average is rising, and the price is well off its yearly low and near its yearly high. Ranking the survivors by 12-month return stands in for relative strength.

The rule Monk.trade uses: common stocks averaging at least $20M traded a day, checked on the last completed session. The close must be above the 50-day average, the 50-day above the 150-day and the 150-day above the 200-day, with the 200-day higher than 21 sessions earlier. The close must be at least 30% above the 52-week low and no more than 25% below the 52-week high.

• Within 10% of the 52-week high

  “Using Monk.trade, run the same trend template on the last completed session, but require the close to be within 10% of the 52-week high. Keep common stocks and the $20M average daily trading value floor, and rank by 12-month return.”

  Open in ChatGPT ↗Open in Claude ↗

  MonkQL

  from stocks
  let s50 = sma(close, 50)
  let s150 = sma(close, 150)
  let s200 = sma(close, 200)
  include type == "common" and sma(close * volume, 20)[2] >= 20000000
  where close[1] > s50[1] and s50[1] > s150[1] and s150[1] > s200[1] and s200[1] > s200[22] and close[1] >= 1.3 * lowest(low, 252)[1] and close[1] >= 0.9 * highest(high, 252)[1]
  show close[1] as prior_close, 100 * (close[1] / close[253] - 1) as return_12m unit percent, 100 * (close[1] / highest(high, 252)[1] - 1) as from_high unit percent
  sort return_12m desc
  take 5
  

• Leave out pending deals

  “Using Monk.trade, run the same trend template on the last completed session, but leave out stocks that filed an 8-K with item 1.01 (a material agreement, such as a merger agreement) or were the subject of a tender offer filing in the last 60 sessions. Rank by 12-month return.”

  Open in ChatGPT ↗Open in Claude ↗

  MonkQL

  from stocks
  let s50 = sma(close, 50)
  let s150 = sma(close, 150)
  let s200 = sma(close, 200)
  include type == "common" and sma(close * volume, 20)[2] >= 20000000
  where close[1] > s50[1] and s50[1] > s150[1] and s150[1] > s200[1] and s200[1] > s200[22] and close[1] >= 1.3 * lowest(low, 252)[1] and close[1] >= 0.75 * highest(high, 252)[1] and not filings(form = "8-k", item = "1.01", window = 60) and not filings(form = "sc to-t", window = 60)
  show close[1] as prior_close, 100 * (close[1] / close[253] - 1) as return_12m unit percent, 100 * (close[1] / highest(high, 252)[1] - 1) as from_high unit percent
  sort return_12m desc
  take 5
  

• Rank by 6-month return

  “Using Monk.trade, run the same trend template on the last completed session, but rank the matches by 6-month price return instead of 12-month.”

  Open in ChatGPT ↗Open in Claude ↗

  MonkQL

  from stocks
  let s50 = sma(close, 50)
  let s150 = sma(close, 150)
  let s200 = sma(close, 200)
  include type == "common" and sma(close * volume, 20)[2] >= 20000000
  where close[1] > s50[1] and s50[1] > s150[1] and s150[1] > s200[1] and s200[1] > s200[22] and close[1] >= 1.3 * lowest(low, 252)[1] and close[1] >= 0.75 * highest(high, 252)[1]
  show close[1] as prior_close, 100 * (close[1] / close[127] - 1) as return_6m unit percent, 100 * (close[1] / highest(high, 252)[1] - 1) as from_high unit percent
  sort return_6m desc
  take 5
  

• Nothing on this page is a signal to buy or sell. Prices can keep moving against you, and you can lose money.
• The query reads the bar before the newest, which is the last completed session while the market is open. Before the open or after the close the newest bar is already complete, so the query reads the session before it. This example ran during the Nov 6 session and read Nov 5. Ask your AI to check the newest session instead.
• The 12-month return is the price change only. Prices account for stock splits but not dividends, and it is not a published relative strength rating.
• Stocks need about 253 sessions of history for the 12-month return and the rising 200-day check. Newer listings are reported as undecided.
• A ranking by return favors stocks that jumped on one piece of news, such as trial results or a buyout offer. Check the chart and recent filings before reading a match as a steady trend.
• Item 1.01 covers any material agreement, including loans and licensing deals, so the pending-deal variation also drops some stocks with no buyout.